Best LLM for long context (2026)
Which models take the largest documents and codebases in one pass?
Rebuilt from live model data · August 3, 2026
How we ranked
Models with a context window of 200K tokens or more, ranked by window size, then intelligence.
Top 3 for long context
- 1
Auto Router
Context window: 2M — in / — out per 1M 2M context 0 providersYour prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...
Vision Tool calling Reasoning Released Nov 8, 2023 - 2
Auto Router (Beta)
Context window: 2M — in / — out per 1M 2M context 0 providersAuto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...
Vision Tool calling Reasoning Released Jul 17, 2026 - 3
Pareto Code Router
Context window: 2M — in / — out per 1M 2M context 0 providersThe Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openroute
Released Apr 21, 2026
Full ranking
| # | Model | Context window | Output / 1M | Context | Providers | Weights |
|---|---|---|---|---|---|---|
| 1 | Auto Router | 2M | — | 2M | 0 | Closed |
| 2 | Auto Router (Beta) | 2M | — | 2M | 0 | Closed |
| 3 | Pareto Code Router | 2M | — | 2M | 0 | Closed |
| 4 | Grok 4.20 | 2M | $2.50 | 2M | 1 | Closed |
| 5 | Grok 4.20 Multi-Agent | 2M | $2.50 | 2M | 1 | Closed |
| 6 | Llama 4 Scout | 1.3M | $0.300 | 1.3M | 4 | Open |
| 7 | GPT-5.6 Sol | 1.1M | $30.00 | 1.1M | 2 | Closed |
| 8 | GPT-5.6 Terra | 1.1M | $7.50 | 1.1M | 2 | Closed |
| 9 | GPT-5.5 | 1.1M | $30.00 | 1.1M | 2 | Closed |
| 10 | GPT-5.4 | 1.1M | $15.00 | 1.1M | 2 | Closed |
| 11 | GPT-5.6 Luna | 1.1M | $3.00 | 1.1M | 2 | Closed |
| 12 | MiMo-V2.5-Pro | 1.1M | $0.696 | 1.1M | 6 | Open |
FAQ
Which models take the largest documents and codebases in one pass?
Auto Router leads for long context with context window 2M, at — per 1M output tokens. Auto Router (Beta) (2M) and Pareto Code Router (2M) follow. Models with a context window of 200K tokens or more, ranked by window size, then intelligence.
How is this ranking produced?
Models with a context window of 200K tokens or more, ranked by window size, then intelligence. The list rebuilds from the live model catalogue on every deploy, so a model that launches or changes price appears here without an editor rewriting the page. Last rebuild: August 3, 2026.
What does the top pick cost to run?
Pricing for Auto Router is not published through OpenRouter.